Pouya Bashivan 🇮🇷🇨🇦
@bashivan.bsky.social
Husband, dad, computational neuroscientist, @mcgillu.bsky.social and Mila
Interesting essay by Tim Dettmers. Although I don’t fully agree with all the predictions, the contrast between China and North America’s approach to practical AI will potentially be defining in years to come
“Why AGI Will Not Happen” by Tim Dettmers.
timdettmers.com/2025/12/10/w...
This essay is worth reading. Discusses diminishing returns (and risks) of scaling. The contrast between West and East: “Winner takes all” approach of building the biggest thing vs a long-term focus on practicality.
timdettmers.com/2025/12/10/w...
This essay is worth reading. Discusses diminishing returns (and risks) of scaling. The contrast between West and East: “Winner takes all” approach of building the biggest thing vs a long-term focus on practicality.
December 15, 2025 at 12:51 PM
Interesting essay by Tim Dettmers. Although I don’t fully agree with all the predictions, the contrast between China and North America’s approach to practical AI will potentially be defining in years to come
Great start at our cognitive benchmarking in large models session at #MontAIN2025 #MAIN2025
December 11, 2025 at 3:47 PM
Great start at our cognitive benchmarking in large models session at #MontAIN2025 #MAIN2025
Attending the Montreal AI and Neuroscience (MAIN) Conference this week? #MontAIN2025
We have put together some exciting educational workshops on cognitive benchmarking large models, RL and video games and dynamical systems! More info and registration here: main-educational.github.io/program/
We have put together some exciting educational workshops on cognitive benchmarking large models, RL and video games and dynamical systems! More info and registration here: main-educational.github.io/program/
Program - MAIN educational 2025
Website of the educational workshop organized during the Montreal Artificial Intelligence and Neuroscience Conference 2025
main-educational.github.io
December 9, 2025 at 3:01 PM
Attending the Montreal AI and Neuroscience (MAIN) Conference this week? #MontAIN2025
We have put together some exciting educational workshops on cognitive benchmarking large models, RL and video games and dynamical systems! More info and registration here: main-educational.github.io/program/
We have put together some exciting educational workshops on cognitive benchmarking large models, RL and video games and dynamical systems! More info and registration here: main-educational.github.io/program/
Reposted by Pouya Bashivan 🇮🇷🇨🇦
For those attending the #CogInterp workshop at NeurIPS, please check out our work on visual symbolic mechanisms led by @rassouel.bsky.social and @thisisadax.bsky.social. We find that visual feature binding in VLMs is supported by emergent symbolic mechanisms.
December 7, 2025 at 6:45 PM
For those attending the #CogInterp workshop at NeurIPS, please check out our work on visual symbolic mechanisms led by @rassouel.bsky.social and @thisisadax.bsky.social. We find that visual feature binding in VLMs is supported by emergent symbolic mechanisms.
Great to see such efforts curating larger scale neuroimaging datasets! Really important for building foundation models for neuroscience!
Need more fMRI data (beyond the amazing NSD)? Introducing MOSAIC! Incredible effort led expertly by Ben Lahner, with help from grad student Mayukh Deb. Work in collaboration with the amazing Aude Oliva! @neurosky.bsky.social. More below..
December 4, 2025 at 5:37 PM
Great to see such efforts curating larger scale neuroimaging datasets! Really important for building foundation models for neuroscience!
Reposted by Pouya Bashivan 🇮🇷🇨🇦
Joint modelling of brain and behaviour dynamics with artificial intelligence
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Joint modelling of brain and behaviour dynamics with artificial intelligence - Nature Reviews Neuroscience
Artificial intelligence is rapidly advancing our mechanistic understanding of the shared structure between the brain and higher-order behaviours. In this Review, Mathis and Mathis synthesize state-of-...
www.nature.com
December 3, 2025 at 4:59 PM
Joint modelling of brain and behaviour dynamics with artificial intelligence
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Reposted by Pouya Bashivan 🇮🇷🇨🇦
We are excited to announce that the Cognitive Computational Neuroscience meeting (CCN 2026) will be held at New York University from August 3–6, 2026.
2026.ccneuro.org
2026.ccneuro.org
December 3, 2025 at 10:01 AM
We are excited to announce that the Cognitive Computational Neuroscience meeting (CCN 2026) will be held at New York University from August 3–6, 2026.
2026.ccneuro.org
2026.ccneuro.org
There’s a lot of debate about “superhuman AI” that might end it for us. All this made me think if that AI, presumably conscious-like, would build even better AI superseding itself? Specially if, it has been trained on these debates. If it choses not to, then it might become the smartest AI ever (?)
December 3, 2025 at 3:59 PM
There’s a lot of debate about “superhuman AI” that might end it for us. All this made me think if that AI, presumably conscious-like, would build even better AI superseding itself? Specially if, it has been trained on these debates. If it choses not to, then it might become the smartest AI ever (?)
Reposted by Pouya Bashivan 🇮🇷🇨🇦
PSA for academics involved in designing admissions systems:
Setting a specific time-of-day deadline is *ri*dic*ul*ous* and super annoying!!!!
Do you really care if I submit this lettter at 6PM rather than 4PM?
Were you planning on reviewing my letter that evening?
Get real...
#academia
Setting a specific time-of-day deadline is *ri*dic*ul*ous* and super annoying!!!!
Do you really care if I submit this lettter at 6PM rather than 4PM?
Were you planning on reviewing my letter that evening?
Get real...
#academia
December 2, 2025 at 12:02 AM
PSA for academics involved in designing admissions systems:
Setting a specific time-of-day deadline is *ri*dic*ul*ous* and super annoying!!!!
Do you really care if I submit this lettter at 6PM rather than 4PM?
Were you planning on reviewing my letter that evening?
Get real...
#academia
Setting a specific time-of-day deadline is *ri*dic*ul*ous* and super annoying!!!!
Do you really care if I submit this lettter at 6PM rather than 4PM?
Were you planning on reviewing my letter that evening?
Get real...
#academia
VLMs are truly caught in the middle! We found that they are great at describing what they see AND great at reasoning from text. But, they fail to connect them without an explicit text bridge. Come talk to us about this and more at #Neurips2025
1/9
🚨Thrilled to share "Caption This, Reason That", a #NeurIPS2025 Spotlight! 🔦
Meet us at #2112, 3 Dec 11 a.m.
We analyze VLM limitations through the lens of Cognitive Science (Perception, Attention, Memory) and propose a simple "Self-Captioning" method that boosts spatial reasoning by ~18%.
🧵👇
🚨Thrilled to share "Caption This, Reason That", a #NeurIPS2025 Spotlight! 🔦
Meet us at #2112, 3 Dec 11 a.m.
We analyze VLM limitations through the lens of Cognitive Science (Perception, Attention, Memory) and propose a simple "Self-Captioning" method that boosts spatial reasoning by ~18%.
🧵👇
December 1, 2025 at 6:06 PM
VLMs are truly caught in the middle! We found that they are great at describing what they see AND great at reasoning from text. But, they fail to connect them without an explicit text bridge. Come talk to us about this and more at #Neurips2025
I still see much focus on single factor coding in studies of medial temporal cortex. Although our results in primate hippocampus indicates a more mixed code
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
November 29, 2025 at 2:14 PM
I still see much focus on single factor coding in studies of medial temporal cortex. Although our results in primate hippocampus indicates a more mixed code
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
Always!
When participating in peer review, always aim to provide high-quality, constructive feedback designed to improve the work. Write reviews that you can proudly stand behind; authors will respect valuable feedback—even when their paper is rejected or your identity is revealed.
November 28, 2025 at 4:50 PM
Always!
Reposted by Pouya Bashivan 🇮🇷🇨🇦
I’m looking for interns to join our lab for a project on foundation models in neuroscience.
Funded by @ivado.bsky.social and in collaboration with the IVADO regroupement 1 (AI and Neuroscience: ivado.ca/en/regroupem...).
Interested? See the details in the comments. (1/3)
🧠🤖
Funded by @ivado.bsky.social and in collaboration with the IVADO regroupement 1 (AI and Neuroscience: ivado.ca/en/regroupem...).
Interested? See the details in the comments. (1/3)
🧠🤖
AI and Neuroscience | IVADO
ivado.ca
November 7, 2025 at 1:52 PM
I’m looking for interns to join our lab for a project on foundation models in neuroscience.
Funded by @ivado.bsky.social and in collaboration with the IVADO regroupement 1 (AI and Neuroscience: ivado.ca/en/regroupem...).
Interested? See the details in the comments. (1/3)
🧠🤖
Funded by @ivado.bsky.social and in collaboration with the IVADO regroupement 1 (AI and Neuroscience: ivado.ca/en/regroupem...).
Interested? See the details in the comments. (1/3)
🧠🤖
The future of Canadian research
November 6, 2025 at 10:59 PM
The future of Canadian research
Reposted by Pouya Bashivan 🇮🇷🇨🇦
Great Blueprint from @arnaghosh.bsky.social on our newest paper on representational geometry!
tl;dr: we find that during pretraining LLMs undergo consistent cycles of expansion/recuction in the dimensionality of their representations & these cycles correlate with the emergence of new capabilities.
tl;dr: we find that during pretraining LLMs undergo consistent cycles of expansion/recuction in the dimensionality of their representations & these cycles correlate with the emergence of new capabilities.
LLMs are trained to compress data by mapping sequences to high-dim representations!
How does the complexity of this mapping change across LLM training? How does it relate to the model’s capabilities? 🤔
Announcing our #NeurIPS2025 📄 that dives into this.
🧵below
#AIResearch #MachineLearning #LLM
How does the complexity of this mapping change across LLM training? How does it relate to the model’s capabilities? 🤔
Announcing our #NeurIPS2025 📄 that dives into this.
🧵below
#AIResearch #MachineLearning #LLM
October 31, 2025 at 4:37 PM
Great Blueprint from @arnaghosh.bsky.social on our newest paper on representational geometry!
tl;dr: we find that during pretraining LLMs undergo consistent cycles of expansion/recuction in the dimensionality of their representations & these cycles correlate with the emergence of new capabilities.
tl;dr: we find that during pretraining LLMs undergo consistent cycles of expansion/recuction in the dimensionality of their representations & these cycles correlate with the emergence of new capabilities.
This sounds like a foundation model for C elegans. Great idea in principle!
Cracking the worm would provide a test bed for how molecular recipes generate neural physiology. And it would allow us to understand how neurons work together to yield emergent brain functions, write @kordinglab.bsky.social and @eboyden3.bsky.social.
www.thetransmitter.org/computationa...
www.thetransmitter.org/computationa...
Whole-brain, bottom-up neuroscience: The time for it is now
Applying new tools to entire brains, starting with C. elegans, offers the opportunity to uncover how molecules work together to generate neural physiology and how neurons work together to generate…
www.thetransmitter.org
October 29, 2025 at 12:04 PM
This sounds like a foundation model for C elegans. Great idea in principle!
Great opportunity to do a postdoc in Canada
🔷 Launch of the IVADO 2026 Postdoctoral Research Funding Program for outstanding national and international postdoctoral researchers.
More info: ivado.ca/en/scholarsh...
#AI #ArtificialIntelligence #R3AI #Funding #Postdoc
More info: ivado.ca/en/scholarsh...
#AI #ArtificialIntelligence #R3AI #Funding #Postdoc
October 27, 2025 at 4:41 PM
Great opportunity to do a postdoc in Canada
For obvious reasons… congrats @yoshuabengio.bsky.social
Congratulations to @yoshuabengio.bsky.social , founder and scientific advisor of Mila, who has become the first researcher in the world to surpass one million citations on Google Scholar, the leading platform for academic and scientific research.
mila.quebec/en/news/ai-r...
mila.quebec/en/news/ai-r...
October 27, 2025 at 3:36 PM
For obvious reasons… congrats @yoshuabengio.bsky.social
Despite the negative feelings about this, I sense some complementary metric like this that measures leadership vs collaboration would be very informative
This is such a horrifically bad idea that I don't even know where to begin.
www.nature.com/articles/d41...
Oh wait, yes I do. I wrote a whole article about it last year: www.thetransmitter.org/publishing/a...
www.nature.com/articles/d41...
Oh wait, yes I do. I wrote a whole article about it last year: www.thetransmitter.org/publishing/a...
Google Scholar tool gives extra credit to first and last authors
Researchers welcome the initiative, but say it doesn’t go far enough to capture the nuance of researcher productivity and impact.
www.nature.com
October 27, 2025 at 11:51 AM
Despite the negative feelings about this, I sense some complementary metric like this that measures leadership vs collaboration would be very informative
Reposted by Pouya Bashivan 🇮🇷🇨🇦
Excellent funding opportunity: $100k/year for two years for a postdoc position in Montreal. Apply if you're interested in joining Montreal's thriving #NeuroAI ecosystem.
🔷 Launch of the IVADO 2026 Postdoctoral Research Funding Program for outstanding national and international postdoctoral researchers.
More info: ivado.ca/en/scholarsh...
#AI #ArtificialIntelligence #R3AI #Funding #Postdoc
More info: ivado.ca/en/scholarsh...
#AI #ArtificialIntelligence #R3AI #Funding #Postdoc
October 16, 2025 at 3:34 PM
Excellent funding opportunity: $100k/year for two years for a postdoc position in Montreal. Apply if you're interested in joining Montreal's thriving #NeuroAI ecosystem.
Reposted by Pouya Bashivan 🇮🇷🇨🇦
BIG ANNOUNCEMENT📣: I haven’t been this excited to be part of something new in 15 years… Thrilled to reveal the passion project I’ve been working on for the past year and a half!🙀🥳 (thread 👇)
October 15, 2025 at 12:22 PM
BIG ANNOUNCEMENT📣: I haven’t been this excited to be part of something new in 15 years… Thrilled to reveal the passion project I’ve been working on for the past year and a half!🙀🥳 (thread 👇)
Consider applying to Mila if you are interested in NeuroAI! There is a great line up of profs working in that area.
P.s. I also have an opening for a PhD student in my lab for Fall 2026.
P.s. I also have an opening for a PhD student in my lab for Fall 2026.
Mila's annual supervision request process is now open to receive MSc and PhD applications for Fall 2026 admission! For more information, visit mila.quebec/en/prospecti...
October 15, 2025 at 7:02 PM
Consider applying to Mila if you are interested in NeuroAI! There is a great line up of profs working in that area.
P.s. I also have an opening for a PhD student in my lab for Fall 2026.
P.s. I also have an opening for a PhD student in my lab for Fall 2026.
Reposted by Pouya Bashivan 🇮🇷🇨🇦
Come join us at University of Toronto. We're hiring a Professor of computational cognitive neuroscience.
#neuroAI #compneuro jobs.utoronto.ca/job/Toronto-...
#neuroAI #compneuro jobs.utoronto.ca/job/Toronto-...
Professor - Computational Cognitive Neuroscience
Professor - Computational Cognitive Neuroscience
jobs.utoronto.ca
September 5, 2025 at 8:22 AM
Come join us at University of Toronto. We're hiring a Professor of computational cognitive neuroscience.
#neuroAI #compneuro jobs.utoronto.ca/job/Toronto-...
#neuroAI #compneuro jobs.utoronto.ca/job/Toronto-...
Reposted by Pouya Bashivan 🇮🇷🇨🇦
If you work on artificial or natural intelligence and are finishing your PhD, consider applying for a Kempner research fellowship at Harvard:
kempnerinstitute.harvard.edu/kempner-inst...
kempnerinstitute.harvard.edu/kempner-inst...
Kempner Research Fellowship - Kempner Institute
The Kempner brings leading, early-stage postdoctoral scientists to Harvard to work on projects that advance the fundamental understanding of intelligence.
kempnerinstitute.harvard.edu
August 18, 2025 at 5:27 PM
If you work on artificial or natural intelligence and are finishing your PhD, consider applying for a Kempner research fellowship at Harvard:
kempnerinstitute.harvard.edu/kempner-inst...
kempnerinstitute.harvard.edu/kempner-inst...
Reposted by Pouya Bashivan 🇮🇷🇨🇦
New position paper! We argue that symbolic and neural network models are not in opposition to each other, but occupy different levels of analysis, and also outline a new research agenda for better understanding the relationship between them. Please check out the paper / thread for more details!
🤖 🧠 NEW PAPER ON COGSCI & AI 🧠 🤖
Recent neural networks capture properties long thought to require symbols: compositionality, productivity, rapid learning
So what role should symbols play in theories of the mind? For our answer...read on!
Paper: arxiv.org/abs/2508.05776
1/n
Recent neural networks capture properties long thought to require symbols: compositionality, productivity, rapid learning
So what role should symbols play in theories of the mind? For our answer...read on!
Paper: arxiv.org/abs/2508.05776
1/n
August 15, 2025 at 4:40 PM
New position paper! We argue that symbolic and neural network models are not in opposition to each other, but occupy different levels of analysis, and also outline a new research agenda for better understanding the relationship between them. Please check out the paper / thread for more details!